© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8862
    Prev
    Next
    INDEX
    Explanations

    as expected

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the verb “work” (in forms like work, works, working) whenever it appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рем
    0.60
     Dent
    0.56
    डील
    0.55
    ков
    0.54
    ंडल
    0.54
    emplate
    0.54
     발
    0.53
     locales
    0.52
    cedent
    0.52
     ഉൾ
    0.52
    POSITIVE LOGITS
    するとき
    0.61
     digraph
    0.59
     fatten
    0.58
     կ
    0.56
     trigonometric
    0.55
     nonconvex
    0.55
     theorists
    0.54
     theorist
    0.53
     minif
    0.51
     கட்சியின்
    0.50
    Activations Density 0.000%

    No Known Activations